|
--- |
|
language: |
|
- "ja" |
|
tags: |
|
- "japanese" |
|
- "token-classification" |
|
- "pos" |
|
license: "cc-by-sa-4.0" |
|
pipeline_tag: "token-classification" |
|
widget: |
|
- text: "国境の長いトンネルを抜けると雪国であった。" |
|
--- |
|
|
|
# roberta-small-japanese-luw-upos |
|
|
|
## Model Description |
|
|
|
This is a RoBERTa model pre-trained on Japanese 青空文庫 texts for POS-tagging, derived from [roberta-small-japanese-aozora](https://huggingface.co/KoichiYasuoka/roberta-small-japanese-aozora). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech). |
|
|
|
## How to Use |
|
|
|
```py |
|
from transformers import AutoTokenizer,AutoModelForTokenClassification,TokenClassificationPipeline |
|
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-small-japanese-luw-upos") |
|
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-small-japanese-luw-upos") |
|
pipeline=TokenClassificationPipeline(tokenizer=tokenizer,model=model,aggregation_strategy="simple") |
|
print([(t["word"],t["entity_group"]) for t in pipeline("国境の長いトンネルを抜けると雪国であった。")]) |
|
``` |
|
|
|
|
